[论文解读] Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection

Zizhao Zhang, Fuyong Xing+3 more|arXiv (Cornell University)|Aug 24, 2017

Medical Image Segmentation Techniques参考文献 197被引用 11

一句话总结

本文综述了近年来利用卷积神经网络（CNNs）进行医学影像轮廓检测的进展，重点介绍了端到端深度学习架构在提升边缘和轮廓检测精度方面相较于传统方法的优势。文章识别出关键挑战，如边缘不连续、医学数据有限以及形状约束问题，并通过迁移学习、多尺度特征融合和形状先验等方法提出解决方案，显著提升了临床影像中的分割性能。

ABSTRACT

The fast growing deep learning technologies have become the main solution of many machine learning problems for medical image analysis. Deep convolution neural networks (CNNs), as one of the most important branch of the deep learning family, have been widely investigated for various computer-aided diagnosis tasks including long-term problems and continuously emerging new problems. Image contour detection is a fundamental but challenging task that has been studied for more than four decades. Recently, we have witnessed the significantly improved performance of contour detection thanks to the development of CNNs. Beyond purusing performance in existing natural image benchmarks, contour detection plays a particularly important role in medical image analysis. Segmenting various objects from radiology images or pathology images requires accurate detection of contours. However, some problems, such as discontinuity and shape constraints, are insufficiently studied in CNNs. It is necessary to clarify the challenges to encourage further exploration. The performance of CNN based contour detection relies on the state-of-the-art CNN architectures. Careful investigation of their design principles and motivations is critical and beneficial to contour detection. In this paper, we first review recent development of medical image contour detection and point out the current confronting challenges and problems. We discuss the development of general CNNs and their applications in image contours (or edges) detection. We compare those methods in detail, clarify their strengthens and weaknesses. Then we review their recent applications in medical image analysis and point out limitations, with the goal to light some potential directions in medical image analysis. We expect the paper to cover comprehensive technical ingredients of advanced CNNs to enrich the study in the medical image domain.

研究动机与目标

• 分析基于CNN的医学影像轮廓检测技术的最新进展。
• 识别医学影像中持续存在的挑战，如边缘不连续、标注数据不足以及形状不一致问题。
• 评估深度学习架构与训练策略在提升轮廓检测性能中的作用。
• 提出将形状先验、迁移学习和多尺度特征学习整合到医学轮廓检测中的技术方向。
• 弥合通用计算机视觉进展与医学影像分析应用之间的差距。

提出的方法

• 采用端到端CNN进行密集像素级轮廓图预测，以全图处理替代基于图像块的推理。
• 通过在自然图像数据集上微调预训练CNN，实现迁移学习，以应对医学训练数据有限的问题。
• 通过连接浅层与深层网络实现多尺度特征融合，以增强边缘检测并保留细节。
• 探索通过损失函数或结构化输出预测整合形状先验，以保持轮廓连续性。
• 研究利用循环神经网络（RNNs）和先进记忆网络建模碎片化轮廓中的长程依赖关系。
• 提出深度监督机制，以提升深层网络的训练稳定性和特征学习能力。

实验结果

研究问题

• RQ1 与传统的基于图像块的方法相比，端到端CNN在医学影像轮廓检测中的性能提升体现在哪些方面？
• RQ2 标准CNN在检测医学影像中不连续或重叠轮廓时的主要局限性是什么？
• RQ3 从自然图像数据集迁移学习在医学数据稀缺场景下，能在多大程度上提升轮廓检测性能？
• RQ4 如何有效将形状先验整合到CNN训练中，以增强轮廓连续性和结构合理性？
• RQ5 多尺度结构与跳跃连接架构在保留医学影像轮廓检测中的细粒度边缘细节方面发挥何种作用？

主要发现

• 端到端CNN在医学影像轮廓检测精度上显著优于传统CNN，甚至超过人类标注者。
• 从自然图像数据集进行迁移学习可提升性能，尤其在医学数据稀缺时，因其可利用早期卷积层中的共享低级特征。
• 多尺度特征融合，特别是浅层与深层之间的跳跃连接，可增强细小边缘的检测并改善轮廓连续性。
• RNN与记忆网络在通过建模边缘序列中的长程依赖关系，实现断裂或不完整轮廓的重建方面展现出潜力。
• 在损失函数或结构化输出层中引入形状先验，有助于保持解剖学合理性并减少分割错误。
• 尽管已取得进展，但在处理重叠细胞、信噪比低的图像以及标注数据有限等问题上仍存在挑战，亟需在弱监督学习与少样本学习方面开展进一步研究。